Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 378 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1313164 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1573580 (Python Code)

Max Activating Token Index: 869

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1412938 (Python Code)

Max Activating Token Index: 729

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1430941 (Python Code)

Max Activating Token Index: 410

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0266. Min Act: -0.0003

Data Index: 673306 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1595032 (Python Code)

Max Activating Token Index: 578

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1645819 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1608826 (Python Code)

Max Activating Token Index: 440

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0282. Min Act: -0.0002

Data Index: 198184 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1411391 (Python Code)

Max Activating Token Index: 1009

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0281. Min Act: -0.0002

Data Index: 477591 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1624510 (Python Code)

Max Activating Token Index: 616

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1213425 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0285. Min Act: -0.0002

Data Index: 526328 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1609326 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1434711 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0259. Min Act: -0.0003

Data Index: 939205 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0284. Min Act: -0.0002

Data Index: 943524 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0269. Min Act: -0.0002

Data Index: 399526 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0262. Min Act: -0.0002

Data Index: 398174 (C4 (Web Text))

Max Activating Token Index: 1005